Business processing method, device and system and nonvolatile storage medium

Abstract

The invention discloses a business processing method, device and system and a nonvolatile storage medium. The method comprises the steps that a target agent receives service processing information, the target agent is any one of multiple agents of a service processing system, the agent corresponds to one or more data models deployed in edge computing nodes, and the data models correspond to one service processing capacity; the computing module is used for executing computing tasks corresponding to business processing capability; a first service processing capability set corresponding to the service processing information is determined, and the first service processing capability set comprises various service processing capabilities required for executing services corresponding to the service processing information; and the target agent calls a data model corresponding to the first service processing capability set to execute the service indicated by the service processing information. The technical problems of high cost and low efficiency caused by adopting a manual auditing mode in related technologies are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, in particular to a business processing method, device, system and non-volatile storage medium. BACKGROUND

[0002] In related technologies, when performing business auditing and other tasks, the commonly used method is manual business auditing. The problem with this method is that the auditing cost is too high and the efficiency is low.

[0003] In view of the above problems, no effective solutions have been proposed so far. SUMMARY

[0004] The embodiments of the present application provide a business processing method, device, system and non-volatile storage medium, to at least solve the technical problem of high cost and low efficiency caused by the manual auditing method in related technologies.

[0005] According to an aspect of an embodiment of the present application, a business processing method is provided, comprising: receiving business processing information by a target agent, wherein the target agent is any one of a plurality of agents of a business processing system, an agent corresponds to one or more data models deployed in an edge computing node, a data model corresponds to a business processing capability, and is used to execute a computing task corresponding to the business processing capability; determining a first business processing capability set corresponding to the business processing information, wherein the first business processing capability set includes various business processing capabilities required to execute a business corresponding to the business processing information; and executing the business indicated by the business processing information by the target agent calling a data model corresponding to the first business processing capability set.

[0006] Optionally, the target agent executing the business indicated by the business processing information by calling the data model corresponding to the first business processing capability set comprises: determining a second business processing capability set corresponding to the target agent; in a case where each business processing capability in the first business processing capability set is in the second business processing capability set, the target agent executes the business indicated by the business processing information by calling a data model corresponding to the target agent; and in a case where there is a target business processing capability in the first business processing capability set that is not in the second business processing capability set, determining a target data model corresponding to the target business processing capability, and calling the target data model by the target agent through an agent corresponding to the target data model to execute the business indicated by the business processing information.

[0007] Optionally, determining the target data model corresponding to the target service processing capability comprises: determining, by the central management node of the service processing system, the target data model corresponding to the target service processing capability; or searching for the target service processing capability in a shared capability list, wherein the shared capability list includes all service processing capabilities corresponding to the agent set in which the target agent is located, and agents corresponding to each service processing capability.

[0008] Optionally, the service processing method further comprises: receiving, by the central management node of the service processing system, a creation request message, wherein the creation request message carries service type information of a to-be-created agent, deployment location information, and service processing capability information; determining, according to the deployment location information, computing resource information of an edge computing node in a region where the deployment location information is located; deploying, according to the computing resource information, a data model corresponding to the service processing capability information in the edge computing node in the region where the deployment location information is located, and establishing an association relationship between the data model and the to-be-created agent.

[0009] Optionally, the service processing method further comprises: determining, by an edge computing node set in the service processing system, a data model set in the set, wherein the data model set information includes data models deployed in each edge computing node in the edge computing node set; determining, according to the data model set, third service processing capability set information, wherein the third service processing capability set information includes service processing capabilities corresponding to each data model in the data model set; generating agent registration information according to the third service processing capability set information and sending the agent registration information to the central management node in the service processing system, wherein the central management node is configured to establish an agent according to the agent registration information.

[0010] Optionally, the service processing method further comprises: determining, by the central management node in the service processing system, a to-be-replicated agent, and a first location and a second location of the agent in the service processing system, wherein the first location is a location of the to-be-replicated agent, and the second location is a deployment location of a replication object of the to-be-replicated agent; determining, by the central management node, a first edge computing node set corresponding to the first location information, and determining deployment information of the to-be-replicated agent according to the edge computing node set, wherein the deployment information includes a data model corresponding to the to-be-replicated agent, topology information of an edge computing node where the data model is located, and computing resource information of the edge computing node; deploying, according to the deployment information, the replication object in a second edge computing node set corresponding to the second location information.

[0011] Optionally, deploying the replication object in the second location according to the deployment information comprises: determining edge computing node computing resource information and node topology information in the second edge computing node set; determining whether the second edge computing node set meets the deployment condition according to the edge computing node computing resource information and the node topology information in the second edge computing node set and the deployment information; and deploying the replication object in the second location according to the deployment information in the case where the deployment condition is met.

[0012] Optionally, the method further comprises: the central management node in the business processing system determining a to-be-migrated agent, and a third location and a fourth location of the agent in the business processing system, wherein the third location is a location where the to-be-migrated agent is located, and the fourth location is a target migration location; the central management node determining a third edge computing node set corresponding to third location information, and determining deployment information of the to-be-migrated agent according to the edge computing node set, wherein the deployment information comprises a data model corresponding to the to-be-migrated agent, topology information of an edge computing node where the data model is located, and computing resource information of the edge computing node; determining whether a fourth edge computing node set corresponding to the fourth location meets a migration condition according to the deployment information; and migrating the to-be-migrated agent and the data model corresponding to the to-be-migrated agent to the fourth location in the case where the migration condition is met.

[0013] According to another aspect of the embodiments of the present application, a business processing system is further provided, comprising a plurality of agents, and a central management node, wherein a target agent receives business processing information, wherein the target agent is any one of the plurality of agents in the business processing system, an agent corresponds to one or more data models deployed in an edge computing node, and a data model corresponds to a business processing capability and is used to execute a computing task corresponding to the business processing capability; a first business processing capability set corresponding to the business processing information is determined, wherein the first business processing capability set comprises various business processing capabilities required to execute a business corresponding to the business processing information; the target agent invokes the data models corresponding to the first business processing capability set to execute a business indicated by the business processing information; and the central management node is used to establish and manage the agents.

[0014] According to another aspect of the embodiments of the present application, a business processing apparatus is also provided, which is applicable to a target intelligent agent, and includes: a first processing module, configured to receive business processing information, wherein the target intelligent agent is any one of a plurality of intelligent agents of a business processing system, each intelligent agent corresponds to one or more data models deployed in an edge computing node, and each data model corresponds to a business processing capability and is configured to execute a computing task corresponding to the business processing capability; a second processing module, configured to determine a first business processing capability set corresponding to the business processing information, wherein the first business processing capability set includes various business processing capabilities required for executing a business corresponding to the business processing information; and a third processing module, configured to invoke the data models corresponding to the first business processing capability set to execute the business indicated by the business processing information.

[0015] According to another aspect of the embodiments of the present application, a nonvolatile storage medium is also provided, which stores a program, wherein the program, when executed, controls a device in which the nonvolatile storage medium is arranged to perform the business processing method.

[0016] According to another aspect of the embodiments of the present application, an electronic device is also provided, which includes a memory and a processor, and the processor is configured to execute a program stored in the memory, wherein the program, when executed, performs the business processing method.

[0017] According to another aspect of the embodiments of the present application, a computer program product is also provided, which includes a computer program, and the computer program, when executed by a processor, implements the business processing method.

[0018] In the embodiments of the present application, the target intelligent agent receives the business processing information, wherein the target intelligent agent is any one of a plurality of intelligent agents of a business processing system, each intelligent agent corresponds to one or more data models deployed in an edge computing node, and each data model corresponds to a business processing capability and is configured to execute a computing task corresponding to the business processing capability; the first business processing capability set corresponding to the business processing information is determined, wherein the first business processing capability set includes various business processing capabilities required for executing a business corresponding to the business processing information; and the target intelligent agent invokes the data models corresponding to the first business processing capability set to execute the business indicated by the business processing information, which determines the business processing capabilities required for executing the business corresponding to the business processing information by the target intelligent agent, and invokes the corresponding data models, so as to achieve the purpose of automatically completing the business processing procedure, thereby achieving the technical effect of reducing the manual processing link in the business processing process, and further solving the technical problems of high cost and low efficiency caused by the manual auditing in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0020] Figure 1 is a flow diagram of a business processing flow according to an embodiment of the application;

[0021] Figure 2 is a structural diagram of a business processing system according to an embodiment of the application;

[0022] Figure 3 is a flow diagram of a business processing method according to an embodiment of the application;

[0023] Figure 4 is a diagram of an agent creation process according to an embodiment of the application;

[0024] Figure 5 is a diagram of an agent replication process according to an embodiment of the application;

[0025] Figure 6 is a diagram of an agent migration process according to an embodiment of the application;

[0026] Figure 7 is a diagram of a business processing process of calling other agents according to an embodiment of the application;

[0027] Figure 8 is a structural diagram of a business processing apparatus according to an embodiment of the application;

[0028] Figure 9 is a structural diagram of an electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0029] In order to make the personnel in the art better understand the application scheme, the technical solutions in the embodiments of the application will be described clearly and completely below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor should be within the scope of protection of the application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0031] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0032] Business audit: it is to check and compare the integrity, consistency and authenticity of business acceptance documents. The traditional audit is mainly in a manual way, and the labor cost is huge, and the audit efficiency is low. Taking a certain provincial company of an operator as an example, the annual audit work order is more than 40 million, and the labor cost of full-service manual audit is nearly 100 million. Through the field of intelligent picture recognition, with the help of AI (Artificial Intelligence) technology, combined with the characteristics of communication industry business, two capabilities of market business AI audit and government enterprise business AI audit can be created to replace manual judgment operation and realize comprehensive intelligent audit of market and government enterprise basic business.

[0033] AI audit business process: the AI audit business process is to return the AI recognition result after the combination service of AI audit preprocessing + AI audit rule + AI core algorithm for the input file transmitted by the application system. The specific business process is as shown in Figure 1 By focusing on the audit business needs in the government and enterprise and market fields, AI technology is applied to solve the intelligent bottleneck of audit, and the AI audit business has covered all high-sensitive business scenarios such as opening an account, replacing a card, password resetting, identity confirmation, transfer, and account closing and reopening, which has significantly improved the digital level of the government and enterprise and market fields.

[0034] At present, based on the application of big data algorithm, the AI audit core algorithm model needs to be continuously optimized and updated in the whole network level, but the individuality and consistency of the business of different regional networks cause that many schemes in the AI audit system can be flexibly deployed while being reused. However, if the same virtual robot or the same processing node is used to implement the audit business in the whole network, it is bound to cause that the node load is too large and the transmission path is too long, which leads to the increase of processing delay and affects the business experience.

[0035] To solve the above problems, the related solutions are provided in the embodiments of the present application, which are described in detail below.

[0036] According to the embodiments of the present application, a method embodiment of a service processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from here.

[0037] The method embodiment provided by the embodiments of the present application can be executed in a service processing system as shown in the accompanying drawings. Figure 2 As can be seen from Figure 2 , the system includes a plurality of agents 22, a central management node 20. Among them, the target agent 22 receives service processing information, wherein the target agent 22 is any one of the plurality of agents 22 of the service processing system, the agent 22 corresponds to one or more data models deployed in the edge computing node, the data model corresponds to a kind of service processing capability, and is used for executing the calculation task corresponding to the service processing capability; determine the first service processing capability set corresponding to the service processing information, wherein the first service processing capability set includes various service processing capabilities required to execute the service corresponding to the service processing information; the target agent 22 calls the data model corresponding to the first service processing capability set to execute the service indicated by the service processing information; the central management node 20 is used to establish and manage the agent 22.

[0038] Optionally, the above-mentioned service processing system can also include an edge management node, wherein the agent 22 can be deployed into the edge management node, and the data processing model loaded in the edge computing node is called through the edge management node.

[0039] The central management node 20 in the embodiments of the present application can be used to uniformly manage the agents 22 deployed to various network edge nodes (edge computing nodes) in the system. The agent 22 can be regarded as a set of one or more service processing capabilities deployed to the edge computing node in the system. Each service processing capability is supported by a corresponding data model.

[0040] In addition, the data model corresponding to one or more service processing capabilities of the agent 22 can be distributedly deployed in one or more physical network computing nodes within the same network area. The agent 22 provides a unified input and output interface or a unified input and output management module for external nodes (such as the central management node 20, a service client or other agents 22). The agent 22 uses a unique ID as an identifier in the system. Figure 2As can be seen, multiple agents 22 can share the same AI service processing capability, that is, a network node deployed with an AI service processing capability can be accessed by multiple agents 22 at the same time. Different agents 22 can have common service processing capabilities, that is, different agents 22 can be associated with and call the same data model.

[0041] In addition, multiple agents 22 can form an agent 22 alliance, that is, within the agent 22 alliance, the capabilities of the agents 22 can be fully shared or a list of sharable capabilities can be determined by the agent 22 alliance. The agent 22 alliance is a logical organization of multiple agents 22 and can not be bound to the physical deployment location of the agents 22, that is, multiple agents 22 that are not deployed in adjacent physical network locations can form an agent 22 alliance according to negotiated rules and determine a list of sharable capabilities within the alliance. The same agent 22 can be included in different virtual robot alliances.

[0042] In some embodiments of the present application, the central management node 20 is responsible for maintaining one or more agent 22 information, including agent 22 ID information, AI service processing capability information, resource information, network topology information, etc. The agent 22 needs to deploy an AI data model supporting the AI service processing capability, and the central management node 20 can not need to deploy an AI data model supporting the AI service processing capability. The agent 22 needs to report an AI service processing capability release / update notification to the central management node 20 when actively updating the AI service processing capability or the AI data model. The agent 22 can indicate to the central management node 20 a list of AI service processing capabilities that it discloses within different agent 22 alliances and a list of AI service processing capabilities that it discloses outside the agent 22 alliance when reporting the AI service processing capability release / update notification to the central management node 20. The agent 22 needs to interact with other agents 22, and can query agent 22 information through the central management node 20 to determine the object to be interacted.

[0043] In the service processing system provided in the embodiments of the present application, by deploying distributed agents 22 (also referred to as virtual robots), and based on edge node cooperation and central node cooperation, virtual robot installation and upgrading, replication and migration, and mutual backup are iteratively completed, the influence of single point failure on the system is avoided while the system capability is flexibly invoked. Not only the system efficiency is improved, but also the user experience of users who need to process services is improved.

[0044] In addition, based on the cooperation between the edge computing nodes and the central management node 20 in the system, the installation and upgrading, replication and migration, and mutual backup of the agents 22 can be implemented, so that the influence of single point failure on the system is avoided while the system capability is flexibly invoked.

[0045] In the above operating environment, the embodiment of the present application provides a service processing method, as shown in Figure 3 The method comprises the following steps:

[0046] In step S302, the target intelligent agent receives service processing information, wherein the target intelligent agent is any one of the plurality of intelligent agents of the service processing system, the intelligent agent corresponds to one or more data models deployed in the edge computing node, and the data model corresponds to a service processing capability for executing a computing task corresponding to the service processing capability.

[0047] In some embodiments of the present application, the above service processing flow includes but is not limited to an auditing service processing flow. The above intelligent agent is also referred to as a virtual robot in the embodiments of the present application.

[0048] In some embodiments of the present application, the central management node can create an intelligent agent in response to a creation request sent by a user or administrator, and the creation process comprises: the central management node of the service processing system receives a creation request message, wherein the creation request message carries service type information, deployment location information, and service processing capability information of the intelligent agent to be created; according to the deployment location information, the computing resource information of the edge computing node in the region where the deployment location information is located is determined; according to the computing resource information, the data model corresponding to the service processing capability information is deployed in the edge computing node in the region where the deployment location information is located, and an association relationship between the data model and the intelligent agent to be created is established.

[0049] In some embodiments of the present application, the process of creating a new intelligent agent by the central management node according to the creation request is as shown in Figure 4 The creation request carries the type of the intelligent agent and / or the service type information of the service it serves, the service volume demand information, the location / region where the intelligent agent is deployed, the network node ID where the intelligent agent is deployed, the intelligent agent capability list information, the ID information of the intelligent agent alliance that the intelligent agent applies to join, the capability list information shared by the intelligent agent in each intelligent agent alliance, and the capability list information shared by the intelligent agent outside the intelligent agent alliance. The intelligent agent type includes a network detection robot (facing network management and maintenance) and a service robot (facing customer service). The service type of the virtual service robot includes account opening, card replacement, password resetting, identity confirmation, transfer, and account cancellation and re-opening. The service volume demand information is, for example, x single A service per day or y bps service transmission. The location / region where the intelligent agent is deployed includes network region ID information, network device ID information, and location GPS information. In addition, one or more intelligent agents can be applied to create by one intelligent agent creation request message.

[0050] As shown in Figure 4As shown, after receiving the creation request, the central management node sends a resource query request to the network nodes in the location / region where the agent is deployed according to the information carried in the creation request. If the agent creation request message carries one or more network node IDs where the agent is deployed indicated by the user, the central management node sends a resource request message to the one or more network nodes where the agent is deployed carried in the agent creation request message. If the agent creation request message does not carry the network node ID information where the agent is deployed indicated by the user, the central management node sends a resource request message to one or more edge computing nodes in the location / region where the agent is deployed required by the agent carried in the agent creation request message. The resource request message carries GPU resource information, CPU resource information, memory information, resource cost information, etc.

[0051] After receiving the resource message fed back by the edge computing node, the central management node can determine one or more AI data models of the agent and send the AI data models to one or more edge computing nodes if the deployment conditions of the newly created agent are met. Each AI data model can support the provision of the capabilities of one or more agents. One AI data model is downloaded and installed by one edge computing node. The set of capabilities provided by the AI data models installed by one or more edge computing nodes constitutes the total set of capabilities of the agent.

[0052] After the agent is successfully deployed, the central management node feeds back a creation success response message to the user who sent the creation request. The message carries the ID of the agent, the capabilities provided by the agent, the AI data model deployment topology information of each capability of the agent, etc.

[0053] In some embodiments of the present application, the set of edge computing nodes in the system can determine the agent to be created by themselves, and the creation process includes: the set of edge computing nodes in the business processing system determines a set of data models in the set, wherein the data model set information includes the data models deployed in each edge computing node in the set of edge computing nodes; according to the set of data models, determine a third business processing capability set information, wherein the third business processing capability set information includes the business processing capabilities corresponding to each data model in the set of data models; according to the third business processing capability set information, generate agent registration information and send it to the central management node in the business processing system, wherein the central management node is used to establish an agent according to the agent registration information.

[0054] In some embodiments of the present application, one or more edge computing nodes can train an innovative intelligent agent through model training in an autonomous domain. The capabilities of the intelligent agent can be jointly provided by one or more AI data models, and one AI data model is downloaded and installed by one network computing node. The set of capabilities provided by the AI data models installed by one or more network computing nodes constitutes the total set of capabilities of the virtual computing person. The edge node determines the ID of the intelligent agent.

[0055] The edge computing node can then send an intelligent agent registration message to the central management node. The registration message carries the type of the intelligent agent and / or the service type information of the intelligent agent, the location / region of the intelligent agent, the network node ID of the intelligent agent, the intelligent agent capability list information, the ID information of the intelligent agent alliance to which the intelligent agent applies to join, the capability list information shared by the intelligent agent in each intelligent agent alliance, and the capability list information shared by the intelligent agent outside the intelligent agent alliance.

[0056] The central management node then records and maintains the registration information of the intelligent agent, and feeds back a registration success message to the edge computing node.

[0057] As an optional implementation, the central management node can implement the replication of the intelligent agent in the following manner: the central management node in the business processing system determines a to-be-replicated intelligent agent and a first location and a second location of the intelligent agent in the business processing system, wherein the first location is the location of the to-be-replicated intelligent agent, and the second location is the deployment location of a replication object of the to-be-replicated intelligent agent; the central management node determines a first edge computing node set corresponding to the first location information, and determines deployment information of the to-be-replicated intelligent agent according to the edge computing node set, wherein the deployment information includes a data model corresponding to the to-be-replicated intelligent agent, topology information of an edge computing node where the data model is located, and computing resource information of the edge computing node; and the replication object is deployed in a second edge computing node set corresponding to the second location information according to the deployment information.

[0058] In some embodiments of the present application, the step of deploying the replication object in the edge computing node set corresponding to the second location information according to the deployment information includes: determining the computing resource information and the node topology structure information of the edge computing nodes in the second edge computing node set; determining whether the second edge computing node set meets the deployment condition according to the computing resource information and the node topology structure information of the edge computing nodes in the second edge computing node set and the deployment information; and deploying the replication object in the second location according to the deployment information in the case where the deployment condition is met.

[0059] In some embodiments of the present application, the replication process of the intelligent agent is as follows: Figure 5The central management node will execute the replication process according to the replication request message. The replication request message can come from the user's agent replication request message, or the central management node determines a virtual robot that can be deployed through replication for an area where an agent is not deployed according to a big data algorithm. The agent replication request message carries the agent ID information, the location / area where the agent is deployed, the network node ID where the agent is deployed, and other information.

[0060] Then the central management node will send an agent information query request to the network node in the location / area where the agent is deployed according to the replicated agent ID information. When the central management node itself maintains all the information required for creating the agent indicated by the agent ID information (including the agent AI data model information, the topology of the nodes required by the innovative agent, and the GPU resource information, CPU resource information, and memory information of each node), and the central management node determines that the information it maintains is the latest version of the agent indicated by the agent ID information, the agent information query request can not be sent.

[0061] The edge management node where the agent to be replicated is located will reply the agent information to the central management node. The agent information includes the agent AI data model information, the topology of the nodes required by the innovative virtual robot, and the GPU resource information, CPU resource information, and memory information of each node.

[0062] Then the central management node will send a resource query request to the network node in the location / area where the new agent is deployed according to the information such as the location / area where the replication object is deployed and the network node ID. If the agent replication request message carries one or more network node IDs where the agent is deployed as indicated by the user, the central management node sends a resource request message to the one or more network nodes where the agent is deployed as carried in the agent replication request message. If the agent replication request message does not carry the network node ID information where the agent is deployed as indicated by the user, the central management node sends a resource request message to one or more network computing nodes in the location / area where the agent is required to be deployed as carried in the agent replication request message. The resource request message carries the GPU resource information, CPU resource information, memory information, resource cost information, and the like.

[0063] After that, the central management node determines whether the replication operation can be continued according to the resource information required by the replication object and the resource information provided by the deployment area. If it is determined that the replication condition is met, the central management node sends one or more AI data models of the agent to one or more edge computing nodes (that is, a second set of edge computing nodes) of the target area network. Each AI data model can support the capability of one or more agents. One AI data model can be downloaded and installed by one edge computing node, or multiple AI data models can be downloaded and installed by the same edge computing node. The set of capabilities provided by the AI data model installed by one or more network computing nodes constitutes the total set of capabilities of the agent.

[0064] After the replication is successful, if the replication request is sent by a user, the central management node feeds back a response message to the user that the agent replication is successful. The message carries the ID of the replication object, the capabilities provided by the replication object, the AI data model deployment topology information of each capability of the replication object, and the like.

[0065] As an optional implementation, the step of migrating the agent by the central management node includes: determining, by the central management node in the business processing system, a to-be-migrated agent and a third position and a fourth position of the agent in the business processing system, where the third position is a position where the to-be-migrated agent is located, and the fourth position is a target migration position; determining, by the central management node, a third set of edge computing nodes corresponding to the third position information, and determining deployment information of the to-be-migrated agent according to the set of edge computing nodes, where the deployment information includes a data model corresponding to the to-be-migrated agent, topology information of an edge computing node where the data model is located, and computing resource information of the edge computing node; determining whether a fourth set of edge computing nodes corresponding to the fourth position meets a migration condition according to the deployment information; and migrating the to-be-migrated agent and the data model corresponding to the to-be-migrated agent to the fourth position in a case where the migration condition is met.

[0066] In some embodiments of the present application, the migration process of the agent is as shown in Figure 6 The central management node can execute the migration process according to migration request information. The migration request information can be migration request information sent by a user or migration request information generated by the central management node according to a preset trigger condition. The migration request information carries ID information of the to-be-migrated agent, source network position / area / edge computing node ID, target network position / area / edge computing node ID, and the like. The source network position is the third position, and the target network position is the fourth position.

[0067] Then the edge management node where the agent to be migrated is located will reply to the center management node with the relevant information of the agent to be migrated, including AI data model information, the topology of the node required for migration of the agent, and GPU resource information, CPU resource information, and memory information of each point.

[0068] Then the edge management node where the agent to be migrated is located will reply to the center management node with the relevant information of the agent to be migrated, including AI data model information, the topology of the node required for migration of the agent, and GPU resource information, CPU resource information, and memory information of each point.

[0069] The center management node will send a resource query request to the fourth edge computing node set indicated by the fourth position. If the agent creation request message carries one or more network node IDs indicated by the user for deployment of the agent, the center management node sends a resource request message to the one or more network nodes for deployment of the agent carried in the agent creation request message. If the agent creation request message does not carry the network node ID information indicated by the user for deployment of the agent, the center management node sends a resource request message to one or more network computing nodes in the position / region required for deployment of the agent carried in the agent creation request message. The resource request message carries GPU resource information, CPU resource information, memory information, resource cost information, and the like.

[0070] Then the center management node will compare the information of the resources required for migration with the information of the resources that can be provided by the fourth edge computing node set to determine whether the migration condition is met. After determining that the migration condition is met, the center management node sends one or more AI data models of the agent to one or more network computing nodes in the target region. The center management node also sends an agent information deletion instruction to the fourth edge computing node set. The instruction carries the ID of the agent to be deleted.

[0071] Finally, in the case where the migration instruction is sent by the user, the center management node will feed back a migration success response message of the agent to the user. The message carries the ID of the agent after migration (which can use the same ID as the agent before migration or be assigned a new ID), the capabilities provided by the agent, and the AI data model deployment topology information of each capability of the agent.

[0072] In step S304, a first service processing capability set corresponding to the service processing information is determined, wherein the first service processing capability set includes various service processing capabilities required for performing the service corresponding to the service processing information.

[0073] In step S306, the target agent calls a data model corresponding to the first service processing capability set to perform the service indicated by the service processing information.

[0074] In the technical solution provided in step S306, the step of the target agent calling a data model corresponding to the first service processing capability set to perform the service indicated by the service processing information includes: determining a second service processing capability set corresponding to the target agent; in a case where each service processing capability in the first service processing capability set is in the second service processing capability set, the target agent calls a data model corresponding to the target agent to perform the service indicated by the service processing information; in a case where there is a target service processing capability in the first service processing capability set that is not in the second service processing capability set, a target data model corresponding to the target service processing capability is determined, and the target data model is called by an agent corresponding to the target data model through the target agent to perform the service indicated by the service processing information.

[0075] In some embodiments of the present application, the step of determining the target data model corresponding to the target service processing capability includes: determining the target data model corresponding to the target service processing capability through a central management node of the service processing system; or searching for the target service processing capability in a shared capability list, wherein the shared capability list includes all service processing capabilities corresponding to an agent set in which the target agent is located, and an agent corresponding to each service processing capability.

[0076] In some embodiments of the present application, as shown in Figure 7 Different agents can provide collaborative services such as mutual assistance and backup. For example, when it is determined that a certain capability required for performing the service indicated by the service processing information is a capability possessed by another agent, the agent can be called to use the capability, thereby performing the service indicated by the service processing information.

[0077] In some embodiments of the present application, the process of the target agent performing the service indicated by the service processing information includes the following steps:

[0078] First, the business client sends a business request to the agent or a network node in the location / region where the agent is deployed, requesting the agent to analyze and process the business. The message carries the business type business ID, and the data content (such as file, photo, signature, etc.) involved in the business. When the business client and the virtual robot are co-located on a physical device, this step can be omitted.

[0079] Second step, the intelligent agent 1 analyzes the service request message according to step 1, and if the processing is successful, it directly enters step 7 to respond to the service. If the service request information is not within the capability range that the intelligent agent 1 can provide or the intelligent agent 1 needs to use backup intelligent agent services due to maintenance, current processing overload, etc., the intelligent agent 1 triggers step 3.

[0080] Third step, the intelligent agent 1 sends an intelligent agent capability query message to the center management node. The message carries information such as service type, service ID, intelligent agent capability requirements, etc.

[0081] Fourth step, the center management node provides the ID information of the intelligent agent capability that meets the service demand or the ID information of the network node it is deployed on according to the intelligent agent capability query message and the intelligent agent capability information table it maintains. When there are multiple intelligent agent capabilities that meet the intelligent agent capability requirements in step 3, the center management node feeds back the ID list of the intelligent agents to the intelligent agent 1, which can be sorted according to the recommended priority. Different intelligent agents can form an intelligent agent alliance (the composition conditions of the intelligent agent alliance are, for example, intelligent agents with close network node physical locations or intelligent agents with data sharing contracts, etc.).

[0082] Fifth step, the intelligent agent 1 selects the intelligent agent 2 according to the ID list of the recommended intelligent agents in step 4 and sends a service analysis processing request to the intelligent agent 2. The message carries information such as service type, service ID, data content involved in the service (such as file, photo, signature, etc.).

[0083] Sixth step, the intelligent agent 2 feeds back the result to the intelligent agent 1 after processing the data.

[0084] Seventh step, the intelligent agent 1 returns the service processing result to the business client.

[0085] By adopting the target intelligent agent to receive the service processing information, wherein the target intelligent agent is any one of the multiple intelligent agents of the service processing system, the intelligent agent corresponds to one or more data models deployed in the edge computing node, the data model corresponds to a service processing capability, and the data model is used to execute a computing task corresponding to the service processing capability; determining a first service processing capability set corresponding to the service processing information, wherein the first service processing capability set includes various service processing capabilities required to execute the service corresponding to the service processing information; and the target intelligent agent executes the service indicated by the service processing information by determining the service processing capability required to execute the service corresponding to the service processing information and calling the corresponding data model, so as to automatically complete the service processing process, thereby achieving the technical effect of reducing the manual processing link in the service processing process, and further solving the technical problems of high cost and low efficiency caused by the manual auditing in the related art.

[0086] The embodiment of the present application provides a service processing device, which is suitable for a target intelligent agent. Figure 8 is a structural schematic diagram of the device. As can be seen from Figure 8 , the device comprises: a first processing module 80, configured to receive service processing information, wherein the target intelligent agent is any one of a plurality of intelligent agents of a service processing system, the intelligent agent corresponds to one or more data models deployed in an edge computing node, the data model corresponds to a service processing capability, and the data model is used for executing a computing task corresponding to the service processing capability; a second processing module 82, configured to determine a first service processing capability set corresponding to the service processing information, wherein the first service processing capability set comprises various service processing capabilities required for executing a service corresponding to the service processing information; and a third processing module 84, configured to call a data model corresponding to the first service processing capability set to execute a service indicated by the service processing information.

[0087] In some embodiments of the present application, the service processing device is further used for: a central management node of the service processing system receiving a creation request message, wherein the creation request message carries service type information, deployment location information and service processing capability information of a to-be-created intelligent agent; determining, according to the deployment location information, computing resource information of an edge computing node in a region where the deployment location information is located; deploying, according to the computing resource information, a data model corresponding to the service processing capability information in the edge computing node in the region where the deployment location information is located, and establishing an association relationship between the data model and the to-be-created intelligent agent.

[0088] In some embodiments of the present application, the service processing device is further used for: a set of edge computing nodes in the service processing system determining a set of data models in the set, wherein the data model set information comprises data models deployed in each edge computing node in the set of edge computing nodes; determining third service processing capability set information according to the data model set, wherein the third service processing capability set information comprises service processing capabilities corresponding to each data model in the data model set; and generating intelligent agent registration information according to the third service processing capability set information and sending the intelligent agent registration information to a central management node in the service processing system, wherein the central management node is used for establishing an intelligent agent according to the intelligent agent registration information.

[0089] In some embodiments of the present application, the business processing apparatus is further configured to: determine, by a central management node in the business processing system, an agent to be replicated and a first location and a second location of the agent in the business processing system, wherein the first location is a location of the agent to be replicated, and the second location is a deployment location of a replication object of the agent to be replicated; determine, by the central management node, a first set of edge computing nodes corresponding to first location information, and determine deployment information of the agent to be replicated according to the set of edge computing nodes, wherein the deployment information includes a data model corresponding to the agent to be replicated, topology information of an edge computing node where the data model is located, and computing resource information of the edge computing node; and deploy the replication object in a second set of edge computing nodes corresponding to second location information according to the deployment information.

[0090] In some embodiments of the present application, the step of deploying, by the business processing apparatus, the replication object in the set of edge computing nodes corresponding to the second location information according to the deployment information includes: determining computing resource information and node topology structure information of edge computing nodes in the second set of edge computing nodes; determining whether the second set of edge computing nodes meets a deployment condition according to the computing resource information and the node topology structure information of the edge computing nodes in the second set of edge computing nodes and the deployment information; and deploying the replication object at the second location according to the deployment information in a case where the deployment condition is met.

[0091] In some embodiments of the present application, the business processing apparatus is further configured to: determine, by a central management node in the business processing system, an agent to be migrated and a third location and a fourth location of the agent in the business processing system, wherein the third location is a location of the agent to be migrated, and the fourth location is a target migration location; determine, by the central management node, a third set of edge computing nodes corresponding to third location information, and determine deployment information of the agent to be migrated according to the set of edge computing nodes, wherein the deployment information includes a data model corresponding to the agent to be migrated, topology information of an edge computing node where the data model is located, and computing resource information of the edge computing node; determine whether a fourth set of edge computing nodes corresponding to the fourth location meets a migration condition according to the deployment information; and migrate the agent to be migrated and the data model corresponding to the agent to be migrated to the fourth location in a case where the migration condition is met.

[0092] In some embodiments of the present application, the third processing module 84 calling the data model corresponding to the first set of business processing capabilities to perform the business indicated by the business processing information includes: determining a second set of business processing capabilities corresponding to the target agent; in a case where each of the business processing capabilities in the first set of business processing capabilities is in the second set of business processing capabilities, the target agent calling the data model corresponding to the target agent to perform the business indicated by the business processing information; in a case where there is a target business processing capability in the first set of business processing capabilities that is not in the second set of business processing capabilities, determining a target data model corresponding to the target business processing capability, and calling the target data model by the target agent through an agent corresponding to the target data model to perform the business indicated by the business processing information.

[0093] In some embodiments of the present application, the third processing module 84 determining the target data model corresponding to the target business processing capability includes: determining the target data model corresponding to the target business processing capability through a central management node of the business processing system; or, searching the target business processing capability in a shared capability list, wherein the shared capability list includes all business processing capabilities corresponding to the agent set in which the target agent is located, and an agent corresponding to each business processing capability.

[0094] It should be noted that each of the modules in the above business processing apparatus can be a program module (for example, a set of program instructions implementing a certain specific function) or a hardware module, and for the latter, it can be in the following form, but is not limited to: each of the above modules is in the form of a processor, or the functions of the above modules are implemented by a processor.

[0095] According to an embodiment of the present application, a non-volatile storage medium is provided, and the non-volatile storage medium stores a program, wherein when the program is running, the device in which the non-volatile storage medium is located performs the following business processing method: a target agent receives business processing information, wherein the target agent is any one of a plurality of agents of a business processing system, an agent corresponds to one or more data models deployed in an edge computing node, and a data model corresponds to a business processing capability for performing a computing task corresponding to the business processing capability; determining a first set of business processing capabilities corresponding to the business processing information, wherein the first set of business processing capabilities includes various types of business processing capabilities required to perform a business corresponding to the business processing information; and the target agent calling a data model corresponding to the first set of business processing capabilities to perform the business indicated by the business processing information.

[0096] According to an embodiment of the present application, a computer program product is provided, comprising a computer program which, when executed by a processor, implements a service processing method as follows: a target agent receives service processing information, wherein the target agent is any one of a plurality of agents of a service processing system, an agent corresponds to one or more data models deployed in an edge computing node, and a data model corresponds to a service processing capability for performing a computing task corresponding to the service processing capability; a first service processing capability set corresponding to the service processing information is determined, wherein the first service processing capability set includes various service processing capabilities required for performing a service corresponding to the service processing information; and the target agent invokes a data model corresponding to the first service processing capability set to perform a service indicated by the service processing information.

[0097] Figure 9 A hardware structure block diagram of an electronic device for implementing a service processing method is shown. As shown in Figure 9 , the electronic device 90 can include one or more (shown in the figure as 902a, 902b, …, 902n) processors 902 (the processor 902 can include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 904 for storing data, and a transmission device 906 for communication functions. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports in the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that Figure 9 The structure shown is only schematic, which does not limit the structure of the above-mentioned electronic device. For example, the electronic device 90 can include more or fewer components than those shown in Figure 9 , or have a different configuration from Figure 9 .

[0098] It should be noted that the one or more processors 902 and / or other data processing circuits described above can be referred to herein as "data processing circuits" in general. The data processing circuit can be embodied in whole or in part as software, hardware, firmware or any combination thereof. In addition, the data processing circuit can be a single independent processing module, or all or part of it can be combined into any one of the other elements in the computer terminal 90 (or mobile device). As referred to in the embodiments of the present application, the data processing circuit serves as a processor to control (for example, selection of a variable resistance terminal path connected to an interface).

[0099] The memory 904 can be used to store software programs of application software and modules, such as program instructions / data storage device corresponding to the business processing method in the embodiments of the present application, and the processor 902 executes various function applications and data processing by running the software programs and modules stored in the memory 904, that is, implements the business processing method described above. The memory 904 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 904 can further include a memory remotely arranged with respect to the processor 902, which can be connected to the electronic device 90 through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0100] The transmission device 906 is used to receive or send data via a network. The specific examples of the above-mentioned network can include a wireless network provided by the communication provider of the electronic device 90. In one example, the transmission device 906 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 906 can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

[0101] The display can be, for example, a touch screen type liquid crystal display (LCD), which can enable the user to interact with the user interface of the electronic device 90.

[0102] In the above-described embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0103] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-described device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0104] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0105] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0106] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part that contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0107] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A business processing method, characterized in that: include: The target agent receives the business processing information, wherein the target agent is any one of multiple agents in the business processing system, the agent corresponds to one or more data models deployed in the edge computing node, the data model corresponds to a business processing capability, and is used to execute a computing task corresponding to the business processing capability; Determining a first business processing capability set corresponding to the business processing information, wherein the first business processing capability set includes various business processing capabilities required to execute the business corresponding to the business processing information; The target agent calls the data model corresponding to the first business processing capability set to execute the business indicated by the business processing information.

2. The service processing method according to claim 1, wherein: The target agent calling the data model corresponding to the first business processing capability set to execute the business indicated by the business processing information includes: Determining a second business processing capability set corresponding to the target agent; In a case where each of the business processing capabilities in the first business processing capability set is included in the second business processing capability set, the target agent calls a data model corresponding to the target agent to execute the business indicated by the business processing information; In the event that there is a target business processing capability in the first business processing capability set that is not in the second business processing capability set, the target data model corresponding to the target business processing capability is determined, and the target agent calls the target data model through the agent corresponding to the target data model to execute the business indicated by the business processing information.

3. The service processing method according to claim 2, characterized in that: Determining the target data model corresponding to the target business processing capability includes: Determine the target data model corresponding to the target business processing capability through the central management node of the business processing system; or The target business processing capability is retrieved from a shared capability list, wherein the shared capability list includes all business processing capabilities corresponding to the agent set where the target agent is located, and agents corresponding to each of the business processing capabilities.

4. The service processing method according to claim 1, wherein: The business processing method further includes: The central management node of the business processing system receives a creation request message, wherein the creation request message carries business type information, deployment location information, and business processing capability information of the agent to be created; Determine computing power resource information of edge computing nodes in the area where the deployment location information is located based on the deployment location information; Based on the computing power resource information, a data model corresponding to the business processing capability information is deployed in the edge computing node in the area where the deployment location information is located, and an association relationship is established between the data model and the intelligent agent to be created.

5. The business processing method according to claim 1, characterized in that: The business processing method further includes: The edge computing node set in the business processing system determines a data model set in a set, wherein the data model set information includes the data model deployed in each edge computing node in the edge computing node set; Determining third service processing capability set information based on the data model set, wherein the third service processing capability set information includes the service processing capability corresponding to each data model in the data model set; Based on the third business processing capability set information, agent registration information is generated and sent to a central management node in the business processing system, wherein the central management node is used to establish an agent based on the agent registration information.

6. The service processing method according to claim 1, characterized in that: The business processing method further includes: The central management node in the business processing system determines an agent to be copied, and a first position and a second position of the agent in the business processing system, wherein the first position is a location of the agent to be copied, and the second position is a deployment location of a copy object of the agent to be copied; The central management node determines a first edge computing node set corresponding to the first location information, and determines deployment information of the to-be-copied agent based on the edge computing node set, wherein the deployment information includes a data model corresponding to the to-be-copied agent, topology information of the edge computing node where the data model is located, and computing power resource information of the edge computing node; The replicated object is deployed in a second edge computing node set corresponding to the second location information according to the deployment information.

7. The service processing method according to claim 6, characterized in that: Deploying the replication object in the edge computing node set corresponding to the second location information according to the deployment information includes: Determine edge computing node computing power resource information and node topology information in the second edge computing node set; Determining whether the second edge computing node set meets the deployment condition based on the edge computing node computing power resource information and the node topology structure information in the second edge computing node set and the deployment information; When the deployment condition is met, the copy object is deployed at the second location according to the deployment information.

8. The service processing method according to claim 1, wherein: The method further comprises: The central management node in the business processing system determines an agent to be migrated, and a third position and a fourth position of the agent in the business processing system, wherein the third position is the position of the agent to be migrated, and the fourth position is the target migration position; The central management node determines a third edge computing node set corresponding to the third location information, and determines deployment information of the to-be-migrated intelligent agent based on the edge computing node set, wherein the deployment information includes a data model corresponding to the to-be-migrated intelligent agent, topology information of the edge computing node where the data model is located, and computing power resource information of the edge computing node; Determining, based on the deployment information, whether the fourth edge computing node set corresponding to the fourth position meets a migration condition; When the migration condition is met, the agent to be migrated and the data model corresponding to the agent to be migrated are migrated to the fourth location.

9. A business processing system, characterized in that: It includes multiple intelligent agents and central management nodes, among which, A target agent receives business processing information, wherein the target agent is any one of multiple agents in a business processing system, the agent corresponds to one or more data models deployed in an edge computing node, the data model corresponds to a business processing capability, and is used to execute a computing task corresponding to the business processing capability; determines a first business processing capability set corresponding to the business processing information, wherein the first business processing capability set includes various business processing capabilities required to execute the business corresponding to the business processing information; and the target agent calls the data model corresponding to the first business processing capability set to execute the business indicated by the business processing information; The central management node is used to establish and manage the intelligent agent.

10. A business processing device, applicable to a target intelligent agent, characterized in that: include: A first processing module is configured to receive business processing information, wherein the target agent is any one of multiple agents in the business processing system, the agent corresponds to one or more data models deployed in the edge computing node, the data model corresponds to a business processing capability, and is configured to execute a computing task corresponding to the business processing capability; a second processing module, configured to determine a first business processing capability set corresponding to the business processing information, wherein the first business processing capability set includes various business processing capabilities required to execute the business corresponding to the business processing information; A third processing module is configured to call a data model corresponding to the first business processing capability set to execute the business indicated by the business processing information.

11. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the service processing method according to any one of claims 1 to 8.

12. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the business processing method according to any one of claims 1 to 8 when running.

13. A computer program product, characterized in that The computer program comprises a computer program, which implements the service processing method according to any one of claims 1 to 8 when executed by a processor.

Images